From a3c9c60168fa0cbc9e18dde4bf7ea7a66b30494a Mon Sep 17 00:00:00 2001 From: "pre-commit-ci[bot]" <66853113+pre-commit-ci[bot]@users.noreply.github.com> Date: Mon, 29 Jun 2026 08:06:01 +0000 Subject: [PATCH] [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --- studio/backend/core/inference/llama_cpp.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/studio/backend/core/inference/llama_cpp.py b/studio/backend/core/inference/llama_cpp.py index d2edfcbd45..cec37609ff 100644 --- a/studio/backend/core/inference/llama_cpp.py +++ b/studio/backend/core/inference/llama_cpp.py @@ -5765,7 +5765,9 @@ class LlamaCppBackend: # mtp_engaged alone is a no-op once budget_frac is set; # pass the byte-accurate overhead so MTP KV is reserved. mtp_engaged = _mtp_will_engage_cpu, - mtp_overhead_fn = (_mtp_bytes if _mtp_will_engage_cpu else None), + mtp_overhead_fn = ( + _mtp_bytes if _mtp_will_engage_cpu else None + ), budget_frac = _CPU_RAM_BUDGET_FRAC, ) _cpu_cap = max(4096, min(_ctx_ceiling, _fit))